← Back to UEFA Champions League center 中文

UEFA Champions League · Score Research

08-19 03:00 CST · UEFA Champions League · Separate HT/FT models

Levski Sofia

Home side / left market direction

Full-time first pick 1:1 Probability 24.8% · Low-total exact zone Low-total exact zone: 1:1 24.8%; 1:2 14.8%; 2:1 10.2% Half-time first pick 0:0 (63.8%)

AEK Athens

Away side / right market direction

Five-Factor Read

1. Market strength Draw carries the highest weight

The handicap leans toward AEK Athens; the market prices the away side as stronger.

2. Form and pace 0:0

HT first pick is 0:0 (63.8%); HT draw probability is 67.2%, so the model still respects early caution.

3. AI Sidecar Read FT total 2.00

This match uses a DeepSeek AI sidecar factor. The AI signal only applies a small candidate-score reweighting and does not override the market/history main model by itself. AI note: 双方节奏与进攻指数偏低，模型最看好1:1，防守平局倾向。客队实力微优但中立场地削弱优势，阵容样本薄导致不确定性高。

4. Venue factor neutral / normal weather

Venue: 阿斯柏鲁卓夫球场. Neutral venue. Weather/temperature: 多云, 26℃～27℃. Neither side has a clear host-country edge, so the venue read mainly removes normal home advantage and pushes the decision back to market, lineup and tournament context. Weather and temperature do not show a clear tempo-suppression signal. Together with the totals line and Under 3.5 probability, the venue layer supports a lower-tempo or lower-margin script rather than pushing the score upward.

5. Sample and soft factors Usable sample

147 comparable matches; useful for probability ranking

Full-Time Score Distribution

1:1 24.8%

1:2 14.8%

2:1 10.2%

2:2 6.5%

0:1 6.1%

1:3 5.7%

0:0 5.2%

1:0 4.5%

FT market: side line -0.25 · total 2.00 · Bucket ah_ou:-0.25/2.0

Score cluster: Low-total exact zone: 1:1 24.8%; 1:2 14.8%; 2:1 10.2%

Half-Time Score Distribution

0:0 63.8%

1:0 14.3%

0:1 13.6%

1:1 3.3%

0:2 1.7%

2:0 1.6%

1:2 0.5%

2:1 0.5%

HT market: side line 0.00 · total 0.75

Levski Sofia win25.9%

Draw37.6%

AEK Athens win36.5%

Levski Sofia expected goals1.28

AEK Athens expected goals1.48

Under 3.573.0%

FT temperature0.95

Empirical weight64.8%

Sample size147

Europe 1X2home 29.8% / draw 30.8% / away 39.3%

Key Variables

First-goal path AEK Athens benefits most from opening the scoring; if HT stays 0:0, the FT distribution compresses toward lower scores.

Deciding factor Draw probability is 37.6%, so the exact-score set should keep draw and one-goal-margin scripts alive.

Risk point Under 3.5 is 73.0%; if the live total moves up materially, rerun the model.

Pre-Match Update · Market Movement

Published 2026-08-25 00:37:43 CST (started/finished about 141h 38m ago) | Snapshot window: pending -> 2026-08-25 00:37:43

First snapshotFT handicap 待补 · total 待补

Latest marketFT handicap -0.25 · total 2

Movement: FT handicap data pending; FT total data pending; HT handicap data pending; HT total data pending.

Pre-match note: Market snapshots are thin; refresh Feijing data again before publishing the final pre-match version.

Final Read: 1:1

Predicted side: draw · Actual side: draw · side aligned

Using the full-time handicap, totals, comparable market buckets and half-time market, the model's full-time first pick for Levski Sofia vs AEK Athens is 1:1 (24.8%). Draw carries the highest weight. This match uses a DeepSeek AI sidecar factor. The AI signal only applies a small candidate-score reweighting and does not override the market/history main model by itself. AI note: 双方节奏与进攻指数偏低，模型最看好1:1，防守平局倾向。客队实力微优但中立场地削弱优势，阵容样本薄导致不确定性高。 HT first pick is 0:0 (63.8%); HT draw probability is 67.2%, so the model still respects early caution. Exact-score outputs are probability rankings for pre-match research and review.

Risk note: exact scores are low-hit-rate events. The model output is a probability ranking, not a certainty; late market moves, lineups, red cards and early goals can reshape the distribution.

Sources

Feijing · fixtures, results, Asian handicap, totals, half-time markets, Europe 1X2 · Local history database · historical market lines, full-time scores, half-time scores · DeepSeek · AI sidecar context, bounded candidate reweighting only